© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23646
    Prev
    Next
    INDEX
    Explanations

    if examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ģä¹Īæĺ¯
    -0.07
    对äºİè¿ĻäºĽ
    -0.07
    usc
    -0.07
    èĩ³å°ij
    -0.06
    对äºİè¿Ļ个
    -0.06
    对è¿ĻäºĽ
    -0.06
     Randall
    -0.06
    rium
    -0.06
    对è¿Ļ个
    -0.06
    æįĹ
    -0.06
    POSITIVE LOGITS
     ãģį
    0.09
    æŁIJä¸Ģ
    0.08
    åľ¨æŁIJ
    0.08
    ancen
    0.08
    `\
    0.08
    æŁIJ人
    0.08
    丽人
    0.07
    æŁIJçļĦ
    0.07
    ť
    0.07
    èµĦ管
    0.07
    Activations Density 0.182%

    No Known Activations